Scholarlink

<p>As new technical paradigms like electronic democracy and e-governance have emerged quickly, large-scale group decision-making (LSGDM) has become a significant area of research. In LSGDM, conflicting interests and divergent viewpoints have grown especially widespread, making it challenging to bring individual preferences into line with a productive group consensus. This paper uses the concept of information granules to design a granular LSGDM consensus framework that addresses two core aspects of LSGDM: the clustering process and the consensus reaching process. First, granular hierarchical clustering is designed based on the principle of justifiable granularity, with a novel division index introduced to determine the optimal number of subgroups. Next, the fuzzy consensus measure is defined by the specificity and coverage of information granule, and a two-stage granule consensus model is proposed by integrating the maximum consensus rule and minimum consensus cost to optimize individual opinions and achieve an efficient group consensus. Finally, an illustrative example with detailed experiments is conducted to demonstrate the practicality and effectiveness of the granular LSGDM consensus model in enhancing consensus and group division among DMs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Granular computing-driven two-stage consensus model for large-scale group decision-making

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月10日

查看全文
  • Yanjun Wang,
  • Xi Chen,
  • Lidong Wang

摘要

As new technical paradigms like electronic democracy and e-governance have emerged quickly, large-scale group decision-making (LSGDM) has become a significant area of research. In LSGDM, conflicting interests and divergent viewpoints have grown especially widespread, making it challenging to bring individual preferences into line with a productive group consensus. This paper uses the concept of information granules to design a granular LSGDM consensus framework that addresses two core aspects of LSGDM: the clustering process and the consensus reaching process. First, granular hierarchical clustering is designed based on the principle of justifiable granularity, with a novel division index introduced to determine the optimal number of subgroups. Next, the fuzzy consensus measure is defined by the specificity and coverage of information granule, and a two-stage granule consensus model is proposed by integrating the maximum consensus rule and minimum consensus cost to optimize individual opinions and achieve an efficient group consensus. Finally, an illustrative example with detailed experiments is conducted to demonstrate the practicality and effectiveness of the granular LSGDM consensus model in enhancing consensus and group division among DMs.